Deep learning improves lens design
An automated scheme for optical lens design looks set to enhance mobile phone cameras.
About
An automated computational approach to the optical lens design of imaging systems promises to provide optimal solutions without human intervention, slashing the time and cost usually required. The result could be improved cameras for mobile phones with superior quality or new functionality.
Developed by Xinge Yang, Qiang Fu and Wolfgang Heidrich at KAUST, the DeepLens design method is based on the concept of “curriculum learning” that uses a structured, iterative, staged approach that considers the imaging system’s key parameters such as its resolution, aperture and field of view.
